Sciweavers

1728 search results - page 233 / 346
» The Accelerated Euclidean Algorithm
Sort
View
IJCNN
2000
IEEE
15 years 6 months ago
A Training Method with Small Computation for Classification
A training data selection method for multi-class data is proposed. This method can be used for multilayer neural networks (MLNN). The MLNN can be applied to pattern classification...
Kazuyuki Hara, Kenji Nakayama
CVPR
2008
IEEE
15 years 4 months ago
Motion blur identification from image gradients
Restoration of a degraded image from motion blurring is highly dependent on the estimation of the blurring kernel. Most of the existing motion deblurring techniques model the blur...
Hui Ji, Chaoqiang Liu
ISLPED
2007
ACM
117views Hardware» more  ISLPED 2007»
15 years 4 months ago
Power signal processing: a new perspective for power analysis and optimization
To address the productivity bottlenecks in power analysis and optimization of modern systems, we propose to treat power as a signal and leverage the rich set of signal processing ...
Quming Zhou, Lin Zhong, Kartik Mohanram
UAI
2003
15 years 4 months ago
Symbolic Generalization for On-line Planning
Symbolic representations have been used successfully in off-line planning algorithms for Markov decision processes. We show that they can also improve the performance of online p...
Zhengzhu Feng, Eric A. Hansen, Shlomo Zilberstein
VCIP
2003
129views Communications» more  VCIP 2003»
15 years 4 months ago
Fast method of segmentation and indexing MPEG1-2 flow
Multimedia data accessibility depends on a precise indexing, involving a computational cost. This paper proposes a new fast method of segmentation and indexing in order to fill o...
Lionel Brunel, Pierre Mathieu